NHL Shot Effectiveness Model

Sasank Vishnubhatla

February 8th, 2019

Last Update: 2019-03-19 10:43:28

Libraries

Before we start, let’s load a few libraries.

rm(list = ls())

options(warn = -1)

library(knitr)
library(ggplot2)
library(caret)
library(doParallel)

registerDoParallel(cores = (detectCores() - 1))

With our libraries loaded we can start loading our data.

Data Loading

Let’s read in our data. Data was downloaded on March 13 at 10:24pm.

data.2015 = read.csv("data/2015.csv")
data.2016 = read.csv("data/2016.csv")
data.2017 = read.csv("data/2017.csv")
data.2018 = read.csv("data/2018.csv")

Now, we will only deal with regular season events. So let’s remove the playoffs from our datasets.

get.regular.season = function(data) {
    subset(data, isPlayoffGame == 0)
}

season.2015 = get.regular.season(data.2015)
season.2016 = get.regular.season(data.2016)
season.2017 = get.regular.season(data.2017)
season.2018 = get.regular.season(data.2018)

Here is a table of all the columns we shall keep and what we shall rename them to.

Old Column Name	New Column Name
`xCordAdjusted`	`x`
`yCordAdjusted`	`y`
`shotAngleAdjusted`	`angle`
`shotDistance`	`dist`
`teamCode`	`team`
`shotType`	`type`
`shooterName`	`shooter`
`goalieNameForShot`	`goalie`

get.helpful.data = function(data) {
    data.frame(x = data$xCordAdjusted,
               y = data$yCordAdjusted,
               angle = data$shotAngleAdjusted,
               dist = data$shotDistance,
               type = data$shotType,
               typeNum = as.numeric(data$shotType),
               goal = data$goal,
               team = data$teamCode,
               shooter = data$shooterName,
               goalie = data$goalieNameForShot)
}

# type:
# 1 -> empty
# 2 -> BACK
# 3 -> DEFL
# 4 -> SLAP
# 5 -> SNAP
# 6 -> TIP
# 7 -> WRAP
# 8 -> WRIST

analysis.2015 = get.helpful.data(season.2015)
analysis.2016 = get.helpful.data(season.2016)
analysis.2017 = get.helpful.data(season.2017)
analysis.2018 = get.helpful.data(season.2018)

Now, we can remove incomplete cases and create our machine learning model’s giant data set.

analysis.2015 = analysis.2015[complete.cases(analysis.2015),]
analysis.2016 = analysis.2016[complete.cases(analysis.2016),]
analysis.2017 = analysis.2017[complete.cases(analysis.2017),]
analysis.all = rbind(analysis.2017, rbind(analysis.2016, analysis.2015))
analysis.all = analysis.all[complete.cases(analysis.all),]
analysis.all = droplevels(analysis.all)
analysis.2018 = analysis.2018[complete.cases(analysis.2018),]
analysis.2018 = droplevels(analysis.2018)

Here’s what analysis.2018 looks like:

analysis.2018

Now, we need a few functions to help us select certain subsets of data. We’ll define three functions: get.team.data, get.shooter.data, get.goalie.data.

get.team.data = function(data, code) {
    subset(data, team == code)
}

get.shooter.data = function(data, code) {
    subset(data, shooter == code)
}

get.goalie.data = function(data, code) {
    subset(data, goalie == code)
}

Calculating Statistics

We can calculate a few statistics, like goal (effective) percentage for a certain shot. Let’s write a function to do that right now.

calculate.goal.percentage = function(data) {
    goals = sum(data$goal == 1)
    total = nrow(data)
    goals / total
}

So, for example, Penguins’s goal percentage against slap shots would be calculated as follows:

penguins.2018 = get.team.data(analysis.2018, "PIT")
penguins.2018.slap = subset(penguins.2018, typeNum == 4)
penguins.2018.slap.eff = calculate.goal.percentage(penguins.2018.slap)

Their goal percentage is 0.0612245.

Here is Ovechkin’s backhand percentage:

ovechkin.2018 = get.shooter.data(analysis.2018, "Alex Ovechkin")
ovechkin.2018.back = subset(ovechkin.2018, typeNum == 2)
ovechkin.2018.back.eff = calculate.goal.percentage(ovechkin.2018.back)

His goal percentage is 0.0833333.

Now, let’s look at Carey Price’s goal percentage against wraparound shots.

price.2018 = get.goalie.data(analysis.2018, "Carey Price")
price.2018.wrap = subset(price.2018, typeNum == 7)
price.2018.wrap.eff = calculate.goal.percentage(price.2018.wrap)

His goal percentage is 0.1052632.

Creating the Models

Using the caret package, we can build machine learning models to help us determine which shot type is best.

Let’s get started with training our control.

control = trainControl(method = "repeatedcv", number = 5, repeats = 3)

Now we will train a few different types of models. Here is a list of the models we will train:

Neural Network
K Nearest Neighbors

model.nnet = train(goal ~ x + y + typeNum + dist + angle,
                   data = analysis.all,
                   method = "nnet",
                   trControl = control)

## # weights:  22
## initial  value 77737.560248 
## iter  10 value 20655.164118
## iter  20 value 18813.075704
## iter  30 value 18771.856595
## iter  40 value 18659.540051
## iter  50 value 18573.913604
## iter  60 value 18530.538848
## iter  70 value 18522.049872
## iter  80 value 18519.265512
## iter  90 value 18512.419443
## iter 100 value 18511.099883
## final  value 18511.099883 
## stopped after 100 iterations

model.knn = train(goal ~ x + y + typeNum + dist + angle,
                  data = analysis.all,
                  method = "knn",
                  trControl = control)

Now our models have been made.

Testing the Models

Let’s test our models on the 2018 data. Here’s what the testing data looks like:

analysis.2018

Now, let’s get our predictions:

nnet.prediction = predict(model.nnet, newdata = analysis.2018, na.action = na.exclude)
knn.prediction = predict(model.knn, newdata = analysis.2018, na.action = na.exclude)

nnet.prediction.data = data.frame(analysis.2018)
nnet.prediction.data$predict = nnet.prediction

knn.prediction.data = data.frame(analysis.2018)
knn.prediction.data$predict = knn.prediction

So, our Neural Network data looks like:

nnet.prediction.data

Our K-Nearest Neighbors data looks like:

knn.prediction.data

Visualizing the Predictions

Let us visualize how distance and the goal prediction are related.

make.knn.dist.plot = function(data, primary, secondary, team) {
    name = paste(team, "Predicted Goal Probability versus Distance (KNN)", sep = " ")
    plot = ggplot(data) +
        geom_smooth(aes(x = dist, y = predict), method = "auto",
                 fill = secondary, color = primary) +
        labs(title = name,
             x = "Distance from Net",
             y = "Probability of Scoring") +
        theme_minimal()
    plot
}

Here’s the same function, but for the neural network data.

make.nnet.dist.plot = function(data, primary, secondary, team) {
    name = paste(team, "Predicted Goal Probability versus Distance (NNet)", sep = " ")
    plot = ggplot(data) +
        geom_smooth(aes(x = dist, y = predict), method = "auto",
                 fill = secondary, color = primary) +
        labs(title = name,
             x = "Distance from Net",
             y = "Probability of Scoring") +
        theme_minimal()
    plot
}

Now let’s visualize the frequency of a shot.

make.type.freq.plot = function(data, primary, secondary, team) {
  name = paste(team, "Frequency per Shot Type", seq = " ")
  plot = ggplot(data) +
    geom_bar(aes(x = type), stat = "count",
                   fill = secondary, color = primary) +
    labs(title = name, x = "Shot Type", y = "Count") +
    theme_minimal()
  plot
}

The next graph is comparing type and goal prediction.

make.knn.type.plot = function(data, primary, secondary, team) {
  name = paste(team, "Predicted Goal versus Shot Type (KNN)", seq = " ")
  plot = ggplot(data) +
    geom_jitter(aes(x = type, y = predict), fill = primary, color = secondary) +
    labs(title = name, x = "Shot Type", y = "Probability of Scoring") +
    theme_minimal()
  plot
}

Here is the neural net flavor of the last function.

make.nnet.type.plot = function(data, primary, secondary, team) {
  name = paste(team, "Predicted Goal versus Shot Type (NNet)", seq = " ")
  plot = ggplot(data) +
    geom_jitter(aes(x = type, y = predict), fill = primary, color = secondary) +
    labs(title = name, x = "Shot Type", y = "Probability of Scoring") +
    theme_minimal()
  plot
}

Examples

Shooters

Forwards

Sidney Crosby

Let’s get our data from the Neural Network and K-Nearest Neighbors algorithms.

crosby.nnet = get.shooter.data(nnet.prediction.data, "Sidney Crosby")
crosby.knn = get.shooter.data(knn.prediction.data, "Sidney Crosby")

Let’s just visualize our shots type data.

crosby.type.freq = make.type.freq.plot(crosby.nnet, "#000000", "#FCB514", "Crosby")

crosby.type.freq

Here is how the Penguins did with shots versus goal probability from the KNN model.

crosby.knn.dist = make.knn.dist.plot(crosby.knn, "#000000", "#FCB514", "Crosby")

crosby.knn.dist

And now with the neural network.

crosby.nnet.dist = make.nnet.dist.plot(crosby.knn, "#000000", "#FCB514", "Crosby")

crosby.nnet.dist

Now let’s look at shot type versus goal probability.

crosby.knn.type = make.knn.type.plot(crosby.knn, "#000000", "#FCB514", "Crosby")

crosby.knn.type

And now with the neural network.

crosby.nnet.type = make.nnet.type.plot(crosby.nnet, "#000000", "#FCB514", "Crosby")

crosby.nnet.type

Alex Ovechkin

Let’s get our data from the Neural Network and K-Nearest Neighbors algorithms.

ovechkin.nnet = get.shooter.data(nnet.prediction.data, "Alex Ovechkin")
ovechkin.knn = get.shooter.data(knn.prediction.data, "Alex Ovechkin")

Let’s just visualize our shots type data.

ovechkin.type.freq = make.type.freq.plot(ovechkin.nnet, "#041E42", "#C8102E", "Ovechkin")

ovechkin.type.freq

Here is how the Penguins did with shots versus goal probability from the KNN model.

ovechkin.knn.dist = make.knn.dist.plot(ovechkin.knn, "#041E42", "#C8102E", "Ovechkin")

ovechkin.knn.dist

And now with the neural network.

ovechkin.nnet.dist = make.nnet.dist.plot(ovechkin.knn, "#041E42", "#C8102E", "Ovechkin")

ovechkin.nnet.dist

Now let’s look at shot type versus goal probability.

ovechkin.knn.type = make.knn.type.plot(ovechkin.knn, "#041E42", "#C8102E", "Ovechkin")

ovechkin.knn.type

And now with the neural network.

ovechkin.nnet.type = make.nnet.type.plot(ovechkin.nnet, "#041E42", "#C8102E", "Ovechkin")

ovechkin.nnet.type

Connor McDavid

mcdavid.nnet = get.shooter.data(nnet.prediction.data, "Connor McDavid")
mcdavid.knn = get.shooter.data(knn.prediction.data, "Connor McDavid")

Let’s just visualize our shots type data.

mcdavid.type.freq = make.type.freq.plot(mcdavid.nnet, "#041E42", "#FF4C00", "McDavid")

mcdavid.type.freq

Here is how the Penguins did with shots versus goal probability from the KNN model.

mcdavid.knn.dist = make.knn.dist.plot(mcdavid.knn, "#041E42", "#FF4C00", "McDavid")

mcdavid.knn.dist

And now with the neural network.

mcdavid.nnet.dist = make.nnet.dist.plot(mcdavid.knn, "#041E42", "#FF4C00", "McDavid")

mcdavid.nnet.dist

Now let’s look at shot type versus goal probability.

mcdavid.knn.type = make.knn.type.plot(mcdavid.knn, "#041E42", "#FF4C00", "McDavid")

mcdavid.knn.type

And now with the neural network.

mcdavid.nnet.type = make.nnet.type.plot(mcdavid.nnet, "#041E42", "#FF4C00", "McDavid")

mcdavid.nnet.type

Elias Pettersson

Let’s get our data from the Neural Network and K-Nearest Neighbors algorithms.

pettersson.nnet = get.shooter.data(nnet.prediction.data, "Elias Pettersson")
pettersson.knn = get.shooter.data(knn.prediction.data, "Elias Pettersson")

Let’s just visualize our shots type data.

pettersson.type.freq = make.type.freq.plot(pettersson.nnet, "#001F5B", "#00843D", "Pettersson")

pettersson.type.freq

Here is how the Penguins did with shots versus goal probability from the KNN model.

pettersson.knn.dist = make.knn.dist.plot(pettersson.knn, "#001F5B", "#00843D", "Pettersson")

pettersson.knn.dist

And now with the neural network.

pettersson.nnet.dist = make.nnet.dist.plot(pettersson.knn, "#001F5B", "#00843D", "Pettersson")

pettersson.nnet.dist

Now let’s look at shot type versus goal probability.

pettersson.knn.type = make.knn.type.plot(pettersson.knn, "#001F5B", "#00843D", "Pettersson")

pettersson.knn.type

And now with the neural network.

pettersson.nnet.type = make.nnet.type.plot(pettersson.nnet, "#001F5B", "#00843D", "Pettersson")

pettersson.nnet.type

Defensemen

Erik Karlsson

Let’s get our data from the Neural Network and K-Nearest Neighbors algorithms.

karlsson.nnet = get.shooter.data(nnet.prediction.data, "Erik Karlsson")
karlsson.knn = get.shooter.data(knn.prediction.data, "Erik Karlsson")

Let’s just visualize our shots type data.

karlsson.type.freq = make.type.freq.plot(karlsson.nnet, "#006D75", "#EA7200", "Karlsson")

karlsson.type.freq

Here is how the Penguins did with shots versus goal probability from the KNN model.

karlsson.knn.dist = make.knn.dist.plot(karlsson.knn, "#006D75", "#EA7200", "Karlsson")

karlsson.knn.dist

And now with the neural network.

karlsson.nnet.dist = make.nnet.dist.plot(karlsson.knn, "#006D75", "#EA7200", "Karlsson")

karlsson.nnet.dist

Now let’s look at shot type versus goal probability.

karlsson.knn.type = make.knn.type.plot(karlsson.knn, "#006D75", "#EA7200", "Karlsson")

karlsson.knn.type

And now with the neural network.

karlsson.nnet.type = make.nnet.type.plot(karlsson.nnet, "#006D75", "#EA7200", "Karlsson")

karlsson.nnet.type

Drew Doughty

Let’s get our data from the Neural Network and K-Nearest Neighbors algorithms.

doughty.nnet = get.shooter.data(nnet.prediction.data, "Drew Doughty")
doughty.knn = get.shooter.data(knn.prediction.data, "Drew Doughty")

Let’s just visualize our shots type data.

doughty.type.freq = make.type.freq.plot(doughty.nnet, "#111111", "#A2AAAD", "Doughty")

doughty.type.freq

Here is how the Penguins did with shots versus goal probability from the KNN model.

doughty.knn.dist = make.knn.dist.plot(doughty.knn, "#111111", "#A2AAAD", "Doughty")

doughty.knn.dist

And now with the neural network.

doughty.nnet.dist = make.nnet.dist.plot(doughty.knn, "#111111", "#A2AAAD", "Doughty")

doughty.nnet.dist

Now let’s look at shot type versus goal probability.

doughty.knn.type = make.knn.type.plot(doughty.knn, "#111111", "#A2AAAD", "Doughty")

doughty.knn.type

And now with the neural network.

doughty.nnet.type = make.nnet.type.plot(doughty.nnet, "#111111", "#A2AAAD", "Doughty")

doughty.nnet.type

Kris Letang

Let’s get our data from the Neural Network and K-Nearest Neighbors algorithms.

letang.nnet = get.shooter.data(nnet.prediction.data, "Kris Letang")
letang.knn = get.shooter.data(knn.prediction.data, "Kris Letang")

Let’s just visualize our shots type data.

letang.type.freq = make.type.freq.plot(letang.nnet, "#000000", "#FCB514", "Letang")

letang.type.freq

Here is how the Penguins did with shots versus goal probability from the KNN model.

letang.knn.dist = make.knn.dist.plot(letang.knn, "#000000", "#FCB514", "Letang")

letang.knn.dist

And now with the neural network.

letang.nnet.dist = make.nnet.dist.plot(letang.knn, "#000000", "#FCB514", "Letang")

letang.nnet.dist

Now let’s look at shot type versus goal probability.

letang.knn.type = make.knn.type.plot(letang.knn, "#000000", "#FCB514", "Letang")

letang.knn.type

And now with the neural network.

letang.nnet.type = make.nnet.type.plot(letang.nnet, "#000000", "#FCB514", "Letang")

letang.nnet.type

Victor Hedman

Let’s get our data from the Neural Network and K-Nearest Neighbors algorithms.

hedman.nnet = get.shooter.data(nnet.prediction.data, "Victor Hedman")
hedman.knn = get.shooter.data(knn.prediction.data, "Victor Hedman")

Let’s just visualize our shots type data.

hedman.type.freq = make.type.freq.plot(hedman.nnet, "#002868", "#C0C0C0", "Hedman")

hedman.type.freq

Here is how the Penguins did with shots versus goal probability from the KNN model.

hedman.knn.dist = make.knn.dist.plot(hedman.knn, "#002868", "#C0C0C0", "Hedman")

hedman.knn.dist

And now with the neural network.

hedman.nnet.dist = make.nnet.dist.plot(hedman.knn, "#002868", "#C0C0C0", "Hedman")

hedman.nnet.dist

Now let’s look at shot type versus goal probability.

hedman.knn.type = make.knn.type.plot(hedman.knn, "#002868", "#C0C0C0", "Hedman")

hedman.knn.type

And now with the neural network.

hedman.nnet.type = make.nnet.type.plot(hedman.nnet, "#002868", "#C0C0C0", "Hedman")

hedman.nnet.type

Goalies

Eastern Conference

Matt Murray

Let’s get our data from the Neural Network and K-Nearest Neighbors algorithms.

murray.nnet = get.goalie.data(nnet.prediction.data, "Matt Murray")
murray.knn = get.goalie.data(knn.prediction.data, "Matt Murray")

Let’s just visualize our shots type data.

murray.type.freq = make.type.freq.plot(murray.nnet, "#000000", "#FCB514", "Murray")

murray.type.freq

Here is how the Penguins did with shots versus goal probability from the KNN model.

murray.knn.dist = make.knn.dist.plot(murray.knn, "#000000", "#FCB514", "Murray")

murray.knn.dist

And now with the neural network.

murray.nnet.dist = make.nnet.dist.plot(murray.nnet, "#000000", "#FCB514", "Murray")

murray.nnet.dist

Now let’s look at shot type versus goal probability.

murray.knn.type = make.knn.type.plot(murray.knn, "#000000", "#FCB514", "Murray")

murray.knn.type

And now with the neural network.

murray.nnet.type = make.nnet.type.plot(murray.nnet, "#000000", "#FCB514", "Murray")

murray.nnet.type

Carey Price

Let’s get our data from the Neural Network and K-Nearest Neighbors algorithms.

price.nnet = get.goalie.data(nnet.prediction.data, "Carey Price")
price.knn = get.goalie.data(knn.prediction.data, "Carey Price")

Let’s just visualize our shots type data.

price.type.freq = make.type.freq.plot(price.nnet, "#AF1E2D", "#192168", "Price")

price.type.freq

Here is how the Penguins did with shots versus goal probability from the KNN model.

price.knn.dist = make.knn.dist.plot(price.knn, "#AF1E2D", "#192168", "Price")

price.knn.dist

And now with the neural network.

price.nnet.dist = make.nnet.dist.plot(price.nnet, "#AF1E2D", "#192168", "Price")

price.nnet.dist

Now let’s look at shot type versus goal probability.

price.knn.type = make.knn.type.plot(price.knn, "#AF1E2D", "#192168", "Price")

price.knn.type

And now with the neural network.

price.nnet.type = make.nnet.type.plot(price.nnet, "#AF1E2D", "#192168", "Price")

price.nnet.type

Braden Holtby

Let’s get our data from the Neural Network and K-Nearest Neighbors algorithms.

holtby.nnet = get.goalie.data(nnet.prediction.data, "Braden Holtby")
holtby.knn = get.goalie.data(knn.prediction.data, "Braden Holtby")

Let’s just visualize our shots type data.

holtby.type.freq = make.type.freq.plot(holtby.nnet, "#041E42", "#C8102E", "Holtby")

holtby.type.freq

Here is how the Penguins did with shots versus goal probability from the KNN model.

holtby.knn.dist = make.knn.dist.plot(holtby.knn, "#041E42", "#C8102E", "Holtby")

holtby.knn.dist

And now with the neural network.

holtby.nnet.dist = make.nnet.dist.plot(holtby.nnet, "#041E42", "#C8102E", "Holtby")

holtby.nnet.dist

Now let’s look at shot type versus goal probability.

holtby.knn.type = make.knn.type.plot(holtby.knn, "#041E42", "#C8102E", "Holtby")

holtby.knn.type

And now with the neural network.

holtby.nnet.type = make.nnet.type.plot(holtby.nnet, "#041E42", "#C8102E", "Holtby")

holtby.nnet.type

Tuukka Rask

Let’s get our data from the Neural Network and K-Nearest Neighbors algorithms.

rask.nnet = get.goalie.data(nnet.prediction.data, "Tuukka Rask")
rask.knn = get.goalie.data(knn.prediction.data, "Tuukka Rask")

Let’s just visualize our shots type data.

rask.type.freq = make.type.freq.plot(rask.nnet, "#F74902", "#000000", "Rask")

rask.type.freq

Here is how the Penguins did with shots versus goal probability from the KNN model.

rask.knn.dist = make.knn.dist.plot(rask.knn, "#F74902", "#000000", "Rask")

rask.knn.dist

And now with the neural network.

rask.nnet.dist = make.nnet.dist.plot(rask.nnet, "#F74902", "#000000", "Rask")

rask.nnet.dist

Now let’s look at shot type versus goal probability.

rask.knn.type = make.knn.type.plot(rask.knn, "#F74902", "#000000", "Rask")

rask.knn.type

And now with the neural network.

rask.nnet.type = make.nnet.type.plot(rask.nnet, "#F74902", "#000000", "Rask")

rask.nnet.type

Western Conference

Ben Bishop

Let’s get our data from the Neural Network and K-Nearest Neighbors algorithms.

bishop.nnet = get.goalie.data(nnet.prediction.data, "Ben Bishop")
bishop.knn = get.goalie.data(knn.prediction.data, "Ben Bishop")

Let’s just visualize our shots type data.

bishop.type.freq = make.type.freq.plot(bishop.nnet, "#006847", "#8F8F8C", "Bishop")

bishop.type.freq

Here is how the Penguins did with shots versus goal probability from the KNN model.

bishop.knn.dist = make.knn.dist.plot(bishop.knn, "#006847", "#8F8F8C", "Bishop")

bishop.knn.dist

And now with the neural network.

bishop.nnet.dist = make.nnet.dist.plot(bishop.nnet, "#006847", "#8F8F8C", "Bishop")

bishop.nnet.dist

Now let’s look at shot type versus goal probability.

bishop.knn.type = make.knn.type.plot(bishop.knn, "#006847", "#8F8F8C", "Bishop")

bishop.knn.type

And now with the neural network.

bishop.nnet.type = make.nnet.type.plot(bishop.nnet, "#006847", "#8F8F8C", "Bishop")

bishop.nnet.type

Jonathan Quick

Let’s get our data from the Neural Network and K-Nearest Neighbors algorithms.

quick.nnet = get.goalie.data(nnet.prediction.data, "Jonathan Quick")
quick.knn = get.goalie.data(knn.prediction.data, "Jonathan Quick")

Let’s just visualize our shots type data.

quick.type.freq = make.type.freq.plot(quick.nnet, "#111111", "#A2AAAD", "Quick")

quick.type.freq

Here is how the Penguins did with shots versus goal probability from the KNN model.

quick.knn.dist = make.knn.dist.plot(quick.knn, "#111111", "#A2AAAD", "Quick")

quick.knn.dist

And now with the neural network.

quick.nnet.dist = make.nnet.dist.plot(quick.nnet, "#111111", "#A2AAAD", "Quick")

quick.nnet.dist

Now let’s look at shot type versus goal probability.

quick.knn.type = make.knn.type.plot(quick.knn, "#111111", "#A2AAAD", "Quick")

quick.knn.type

And now with the neural network.

quick.nnet.type = make.nnet.type.plot(quick.nnet, "#111111", "#A2AAAD", "Quick")

quick.nnet.type

Mikko Koskinen

Let’s get our data from the Neural Network and K-Nearest Neighbors algorithms.

koskinen.nnet = get.goalie.data(nnet.prediction.data, "Mikko Koskinen")
koskinen.knn = get.goalie.data(knn.prediction.data, "Mikko Koskinen")

Let’s just visualize our shots type data.

koskinen.type.freq = make.type.freq.plot(koskinen.nnet, "#041E42", "#FF4C00", "Koskinen")

koskinen.type.freq

Here is how the Penguins did with shots versus goal probability from the KNN model.

koskinen.knn.dist = make.knn.dist.plot(koskinen.knn, "#041E42", "#FF4C00", "Koskinen")

koskinen.knn.dist

And now with the neural network.

koskinen.nnet.dist = make.nnet.dist.plot(koskinen.nnet, "#041E42", "#FF4C00", "Koskinen")

koskinen.nnet.dist

Now let’s look at shot type versus goal probability.

koskinen.knn.type = make.knn.type.plot(koskinen.knn, "#041E42", "#FF4C00", "Koskinen")

koskinen.knn.type

And now with the neural network.

koskinen.nnet.type = make.nnet.type.plot(koskinen.nnet, "#041E42", "#FF4C00", "Koskinen")

koskinen.nnet.type

Marc-Andre Fleury

Let’s get our data from the Neural Network and K-Nearest Neighbors algorithms.

fleury.nnet = get.goalie.data(nnet.prediction.data, "Marc-Andre Fleury")
fleury.knn = get.goalie.data(knn.prediction.data, "Marc-Andre Fleury")

Let’s just visualize our shots type data.

fleury.type.freq = make.type.freq.plot(fleury.nnet, "#B4975A", "#333F42", "Fleury")

fleury.type.freq

Here is how the Penguins did with shots versus goal probability from the KNN model.

fleury.knn.dist = make.knn.dist.plot(fleury.knn, "#B4975A", "#333F42", "Fleury")

fleury.knn.dist

And now with the neural network.

fleury.nnet.dist = make.nnet.dist.plot(fleury.nnet, "#B4975A", "#333F42", "Fleury")

fleury.nnet.dist

Now let’s look at shot type versus goal probability.

fleury.knn.type = make.knn.type.plot(fleury.knn, "#B4975A", "#333F42", "Fleury")

fleury.knn.type

And now with the neural network.

fleury.nnet.type = make.nnet.type.plot(fleury.nnet, "#B4975A", "#333F42", "Fleury")

fleury.nnet.type

Teams

Eastern Conference

Pittsburgh Penguins

Let’s get our data from the Neural Network and K-Nearest Neighbors algorithms.

pit.nnet = get.team.data(nnet.prediction.data, "PIT")
pit.knn = get.team.data(knn.prediction.data, "PIT")

Let’s just visualize our shots type data.

pit.type.freq = make.type.freq.plot(pit.nnet, "#000000", "#FCB514", "PIT")

pit.type.freq

Here is how the Penguins did with shots versus goal probability from the KNN model.

pit.knn.dist = make.knn.dist.plot(pit.knn, "#000000", "#FCB514", "PIT")

pit.knn.dist

And now with the neural network.

pit.nnet.dist = make.nnet.dist.plot(pit.nnet, "#000000", "#FCB514", "PIT")

pit.nnet.dist

Now let’s look at shot type versus goal probability.

pit.knn.type = make.knn.type.plot(pit.knn, "#000000", "#FCB514", "PIT")

pit.knn.type

And now with the neural network.

pit.nnet.type = make.nnet.type.plot(pit.nnet, "#000000", "#FCB514", "PIT")

pit.nnet.type

Tampa Bay Lightning

Let’s get our data from the Neural Network and K-Nearest Neighbors algorithms.

tbl.nnet = get.team.data(nnet.prediction.data, "T.B")
tbl.knn = get.team.data(knn.prediction.data, "T.B")

Let’s just visualize our shots type data.

tbl.type.freq = make.type.freq.plot(tbl.nnet, "#002868", "#AAB1BF", "T.B")

tbl.type.freq

Here is how the Lightning did with shots versus goal probability from the KNN model.

tbl.knn.dist = make.knn.dist.plot(tbl.knn, "#002868", "#AAB1BF", "T.B")

tbl.knn.dist

And now with the neural network.

tbl.nnet.dist = make.nnet.dist.plot(tbl.nnet, "#002868", "#AAB1BF", "T.B")

tbl.nnet.dist

Now let’s look at shot type versus goal probability.

tbl.knn.type = make.knn.type.plot(tbl.knn, "#002868", "#AAB1BF", "T.B")

tbl.knn.type

And now with the neural network.

tbl.nnet.type = make.nnet.type.plot(tbl.nnet, "#002868", "#AAB1BF", "T.B")

tbl.nnet.type

Washington Capitals

Let’s get our data from the Neural Network and K-Nearest Neighbors algorithms.

wsh.nnet = get.team.data(nnet.prediction.data, "WSH")
wsh.knn = get.team.data(knn.prediction.data, "WSH")

Let’s just visualize our shots type data.

wsh.type.freq = make.type.freq.plot(wsh.nnet, "#041E42", "#C8102E", "WSH")

wsh.type.freq

Here is how the Cawshals did with shots versus goal probability from the KNN model.

wsh.knn.dist = make.knn.dist.plot(wsh.knn, "#041E42", "#C8102E", "WSH")

wsh.knn.dist

And now with the neural network.

wsh.nnet.dist = make.nnet.dist.plot(wsh.nnet, "#041E42", "#C8102E", "WSH")

wsh.nnet.dist

Now let’s look at shot type versus goal probability.

wsh.knn.type = make.knn.type.plot(wsh.knn, "#041E42", "#C8102E", "WSH")

wsh.knn.type

And now with the neural network.

wsh.nnet.type = make.nnet.type.plot(wsh.nnet, "#041E42", "#C8102E", "WSH")

wsh.nnet.type

Western Conference

Vegas Golden Knights

Let’s get our data from the Neural Network and K-Nearest Neighbors algorithms.

vgk.nnet = get.team.data(nnet.prediction.data, "VGK")
vgk.knn = get.team.data(knn.prediction.data, "VGK")

Let’s just visualize our shots type data.

vgk.type.freq = make.type.freq.plot(vgk.nnet, "#B4975A", "#333F42", "VGK")

vgk.type.freq

Here is how the Golden Knights did with shots versus goal probability from the KNN model.

vgk.knn.dist = make.knn.dist.plot(vgk.knn, "#B4975A", "#333F42", "VGK")

vgk.knn.dist

And now with the neural network.

vgk.nnet.dist = make.nnet.dist.plot(vgk.nnet, "#B4975A", "#333F42", "VGK")

vgk.nnet.dist

Now let’s look at shot type versus goal probability.

vgk.knn.type = make.knn.type.plot(vgk.knn, "#B4975A", "#333F42", "VGK")

vgk.knn.type

And now with the neural network.

vgk.nnet.type = make.nnet.type.plot(vgk.nnet, "#B4975A", "#333F42", "VGK")

vgk.nnet.type

Colorado Avalance

Let’s get our data from the Neural Network and K-Nearest Neighbors algorithms.

col.nnet = get.team.data(nnet.prediction.data, "COL")
col.knn = get.team.data(knn.prediction.data, "COL")

Let’s just visualize our shots type data.

col.type.freq = make.type.freq.plot(col.nnet, "#6F263D", "#236192", "COL")

col.type.freq

Here is how the Avalance did with shots versus goal probability from the KNN model.

col.knn.dist = make.knn.dist.plot(col.knn, "#6F263D", "#236192", "COL")

col.knn.dist

And now with the neural network.

col.nnet.dist = make.nnet.dist.plot(col.nnet, "#6F263D", "#236192", "COL")

col.nnet.dist

Now let’s look at shot type versus goal probability.

col.knn.type = make.knn.type.plot(col.knn, "#6F263D", "#236192", "COL")

col.knn.type

And now with the neural network.

col.nnet.type = make.nnet.type.plot(col.nnet, "#6F263D", "#236192", "COL")

col.nnet.type

Calgary Flames

Let’s get our data from the Neural Network and K-Nearest Neighbors algorithms.

cgy.nnet = get.team.data(nnet.prediction.data, "CGY")
cgy.knn = get.team.data(knn.prediction.data, "CGY")

Let’s just visualize our shots type data.

cgy.type.freq = make.type.freq.plot(cgy.nnet, "#C8102E", "#F1BE48", "CGY")

cgy.type.freq

Here is how the Flames did with shots versus goal probability from the KNN model.

cgy.knn.dist = make.knn.dist.plot(cgy.knn, "#C8102E", "#F1BE48", "CGY")

cgy.knn.dist

And now with the neural network.

cgy.nnet.dist = make.nnet.dist.plot(cgy.nnet, "#C8102E", "#F1BE48", "CGY")

cgy.nnet.dist

Now let’s look at shot type versus goal probability.

cgy.knn.type = make.knn.type.plot(cgy.knn, "#C8102E", "#F1BE48", "CGY")

cgy.knn.type

And now with the neural network.

cgy.nnet.type = make.nnet.type.plot(cgy.nnet, "#C8102E", "#F1BE48", "CGY")

cgy.nnet.type